首页> 外文期刊>Multimedia Tools and Applications >A software supported image enhancement approach based on DCT and quantile dependent enhancement with a total control on enhancement level
【24h】

A software supported image enhancement approach based on DCT and quantile dependent enhancement with a total control on enhancement level

机译:一种基于软件的图像增强方法,基于DCT和分位数相关的增强,完全控制增强级别

获取原文
获取原文并翻译 | 示例
           

摘要

In many computer vision applications like medical imaging, pattern recognition etc., image enhancement is an important pre-processing requirement which is used to improve the efficiency of an application. A significantly large literature is available on image enhancement; unfortunately, most of these schemes have certain shortcomings for e.g. the lack of control over the contrast starching, noise enhancement and mean-shift' problem etc. To deal with the aforementioned problems, this study suggests an efficient method which is based on discrete cosine transformation (DCT) and quantile dependent sub-division of the histogram of given input image. In the proposed method, we apply DCT on the input image to get low-frequency component (LFC) and then use the quantile-based sub-division on the histogram of LFC. Finally, histogram equalization is performed on all these sub-histograms separately. The main advantage of quantile-based segmentation is that here entire intensity spectrum participates in the enhancement process, which provides a total control over the enhancement level. In the proposed method the high-frequency component remains untouched and hence the structural information of the input image and the noise in the input image remains unaffected by the image enhancement process.
机译:在许多计算机视觉应用中,例如医学成像,模式识别等,图像增强是重要的预处理要求,用于提高应用效率。有关图像增强的大量文献可供参考;不幸的是,这些方案中的大多数都有某些缺点,例如。为了解决上述问题,本研究提出了一种有效的方法,该方法基于离散余弦变换(DCT)和分位数的细分给定输入图像的直方图。在提出的方法中,我们在输入图像上应用DCT以获得低频分量(LFC),然后在LFC的直方图上使用基于分位数的细分。最后,对所有这些子直方图分别执行直方图均衡化。基于分位数的分割的主要优势在于,整个强度谱都参与了增强过程,从而可以完全控制增强水平。在所提出的方法中,高频分量保持不变,因此输入图像的结构信息和输入图像中的噪声不受图像增强处理的影响。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号